DIMENSION DECREASING OF FEATURE SPACE
Eva Ocelíková, Dana KLIMEäOVÁ, Iveta Zolotová · 2008
A big number of monitored features in examined obj ects often complicates a technical realization of d ecision-making and extends the time necessary for providing a decision . It is possible to decrease dimensionality of the tasks and along with not to decrease a quality of decision-making. The main sub ject of this contribution relates to some of the possible approaches. Basis of these methods stays in finding a linear transformat ion of original m-dimensional space of features int o a new n-dimensional feature space where n m ≤ . New features are arisen by suitable linear combinat ion of original features and they are descending so rted according to their variance. The contribution descr ibes experience and results obtained with the decrea sing of feature space and the classification of sets of the objects which where re presented by real pictures of the Earth surface.